Associate Professor Irina-Maria DRAGAN, PhD

Professor Alexandru ISAIC-MANIU, PhD

E-mail: irina.dragan@csie.ase.ro
The Bucharest Academy of Economic Studies

CHARACTERIZING THE FREQUENCY OF EARTHQUAKE

INCIDENCE IN ROMANIA

Abstract. From a seismic point of view, Romania is dominated of events in

one region, Vrancea. In the past 300 years, a single major seismic event occurred
with an epicenter outside this area (1916). This paper starts from going over all
major seismic events, with a magnitude of over 6 degrees on Richters scale, which
were documented. Was tested the most plausible statistic behavioral model and
was determined the probabilities for future large scale earthquakes, by different
time horizons.
Key Words: seismic risk, statistic model, modeling, validation, statistic
prediction, statistic distribution.
JEL Classification: C52, C13, C46, Q54

1. GENERAL ASPECTS
As it is well-known, the occurrence of major seismic phenomena is a rare event
from a statistical point of view. Due to the very large time horizon that can be
taken into observation as against to registering events in artificial systems, as well
as the non-periodicity of these events, there is the possibility of interpretation and
statistical modeling of these seismic phenomena. In Romanian: Dragomir (2009),
Lungu (1999), Lungu and Arion (2000), Radulescu (2004).
The statistical studies regarding the earthquakes usually start from the fact that rare
events are best described using the exponential law if considering the succession
of time intervals between events, or Poissons law if it is intended to model the
frequency of earthquakes (Scuiu and Zorilescu, 1978; Johnson, Kotz and
Balakrishnan, 1994; Evans, Hasting and Peacock, 2000).
The easiness of using these two distribution laws, distinct in nature, consists of the
fact that they are defined by the same parameter, characterizing the same
phenomenon the behavior of a system in time, from both continuous and discrete
points of view. A previous study made on seismic phenomena in Romania (Voda
and Isaic-Maniu, 1983) covering the time period 1400-2000, has failed to confirm
the hypothesis of an exponential behavior, the confirmed model being the biparametric Weibull model.

Irina Maria Dragan, Alexandru Isaic-Maniu

__________________________________________________________________
In the followings, we shall extend the area of investigation starting with the year
1100, with some additions to the identified supplementary information, as well as
to the earthquake in 1977, the last one taken into account in the previous study.
We considered major seismic events those with a level of over 6 degrees on
Richters scale. Obviously, historical assessments are somewhat subjective, as the
intensity was evaluated indirectly, since Mercalli (1931) and Richters (1956)
scales are more recent. The chronicles used to register that: the earth had been
shaken and the bells were ringing by themselves in Golias tower (n.n. Iasi
Romania), which indicates that an important seismic event took place. We used
information in the profile literature (Constantinescu and Marza, 1980) as well as
other official sources as those of the National Institute for the Physics of Earth
(www.infp.ro).

2. THE OCCURRENCE OF MAJOR SEISMIC EVENTS

The main seismic events which occurred in Romania, and their characteristics, as
they were recorded at the time in documents, or in modern and official
registrations, were:
- November 5th, 1107, 6.2 degrees Richter
- August 8th, 1126, 6.2 degrees Richter
- April 1st, 1170, 7.0 degrees Richter
- February 13th, 7.0 degrees Richter
- May 10th, 1230, 7.1 Richter
- year 1276, 6.5 degrees Richter
- year 1327, 7.0 degrees Richter
- October 10th, 1446, 7.3 degrees Richter
- August 29th, 1471, 12 oclock, 7.1 degrees Richter. This earthquake took place
not long before the wedding of Stefan the Great, sovereign of Moldova, with Maria
of Mangop, and it was described by chronicler Grigore Ureche: while Stefan the
Great sat at the table in the Citadel of Suceava, a wing in Nebuisei Tower fell
crumbling down.
- November 24th, 1516, 7.2 degrees Richter
- July 19th, 1545, 6.7 degrees Richter
- November 2nd, 1558, 6.1 degrees Richter
- August 17th, 1569, 6.7 degrees Richter
- May 10th, 1590, 6.5 degrees Richter
- August 10th, 1590, 6.1 degrees Richter
- August 4th, 1599, 6.1 degrees Richter
- May 3rd, 1604, 6.7 degrees Richter
- November 24th 1605, 6.7 degrees Richter
- January 13th, 1606 6.4 degrees Richter
- October 8th, 1620, 10:55, 7-8 degrees Richter (some sources indicate 7.9).
The most active area in Romania, seismic wise, is Vrancea, and the shock waves
affect the South and South-East areas of Romania, including the capital, Bucharest
(Radulian, 2004; Lungu, Arion, Baur and Aldea, 2000; Ivan, 2007; Ardeleanu,
1999; Constantinescu and Mrza, 1980; www.incerc2004.ro).

Characterizing the Frequency of Earthquake Incidence in Romania

__________________________________________________________________
Urban areas in that time were very few and quite primitive, so that material
damages were minor. The buildings affected from this earthquake were churches
and monasteries, the only ones which were more considerable.
- August 9th, 1679, 6.8 degrees Richter
- August 8th, 1681, 6.7 degrees Richter
- June 12th, 1701, 7.1 degrees Richter
- October 11th, 1711, 6.1 degrees Richter
- May 31st, 1738, 7.0 degrees Richter during the reign of Constantine
Mavrocordat. In a Greek recording there is also mention of a terrible earthquake
and in a church book another recording state that on May 31st, at 3 oclock in the
morning there was an earthquake and earth has opened and water came out with a
smell of gun powder and sulfur.
- December 7th, 1746, 6.5 degrees Richter
- year 1750, 6.0 degrees Richter
- January 18th, 1778, 6.1 degrees Richter
- March 18th, 1784, 5.8 degrees Richter
- April 6th, 1790, 7-8 degrees Richter
- December 8th, 1793, 6.1 degrees Richter
- October 26th, 1802, 12:55 PM, 7.9 degrees Richter, depth of 150 km in
Bucharest, the earthquake lasted for 2 minutes and a half, the chronicles and church
recordings state that the towers of the holy churches fell, and other churches fell
entirely and also that in Bucharest the high tower of Coltea, the wonder of the
city, was broken, and few of the mansions and public constructions made it
soundlyand also, many of the wooden houses in Bucharest were burnt. The
tower was built between 1709-1714 as observance point (50 m high) and the belfry
of Coltea monastery. At its construction, the royal troops of Carol XII of Sweden
participated, as they were retreating from the battle of Poltava in the War of the
North (June 27-July 8, 1709).
- March 5th, 1812 (2:30 AM) 6.5 degrees Richter, 130 km in depth.
- January 5th, 1823, 6.0 degrees Richter
- November 26th, 1829 (8:45 PM), 7.5 degrees Richter, 150 km in depth, 1 minute
duration, the deacon of Batistea church wrote: it was almost as the earthquake in
1802, October.
- October 15th, 1834, 6.0 degrees Richter
- January 23rd, 1838, 8:45 PM, 7.5 degrees Richter, 150 km in depth (the police
prefects report states that there were 8 people dead, 14 injured, 36 houses entirely
damaged, and many with serious damages). The Coltea tower was almost
completely destroyed, and was demolished in 1888 when the boulevard was
modernized. Later on, the subway works in the 1970s highlight the foundation,
marked by marble flagstones engraved in the asphalt, but covered later, at repairs
made in the road.
- October 15th, 1847, 6.2 degrees Richter
- October 17th, 1859, 6.0 degrees Richter
- April 27th, 1865, 6.4 degrees Richter
- November 13th, 1868 6.0 degrees Richter
- November 23rd, 1868, 6.5 degrees Richter

Irina Maria Dragan, Alexandru Isaic-Maniu

__________________________________________________________________
- November 26th 1868, 6.1 degrees Richter
- October 10th, 1879, 6.2 degrees Richter
- August 31st, 1894, 7.1 degrees Richter (during this earthquake the riversides of
Prut river were damaged on a length of over 500 meters in the county of Galati,
and many old houses in the suburbs of Bucharest were also considerably damaged)
- September 13th, 1903, 6.3 degrees Richter
- October 6th, 1908 (11:40 PM), 7.1 degrees Richter, 125 km in depth it was an
earthquake which manifested in 3 consecutive phases, more and more powerful,
and lasted approximately 3 minutes. It damaged especially the old houses in
Bucharest, in the East of Muntenia and the South of Moldova.
- May 25th, 1912, 6.3 degrees Richter
- January 26th, 1916, 6.4 degrees Richter
- March 29th, 1934, 6.9 degrees Richter
- November 10th, 1940 (1:39 AM). It had a magnitude of 7.7 degrees Richter, 133
km in depth. The effects were devastating in the center and South of Moldova, as
well as in Muntenia. The number of the victims was estimated to 1000 deaths and
4000 injured most of them in Moldova. Due to the context created, the exact
number of casualties was never known, the information being censured during the
war. In Bucharest, many other apartment buildings were considerably damaged.
The Carlton construction was destroyed in that occasion, an architectural pride in
the Bucharest of the time, the highest construction at the time, placed at the
intersection of Royal Street and Bratianu Boulevard (Balcescu Boulevard
nowadays). The contemporaries say that no one was salvaged from the
approximately 300 persons found in the building. Among the dead, there was also
I. Vasilache, famous composer and singer at the time, member of the musical and
comedian couple Stroe and Vasilache.
- March 4th, 1977 (9:22 PM), 7.4 degrees Richter, 94 km in depth lasted
approximately 55 seconds, and caused 1578 victims, of which 1424 in Bucharest.
At the level of the entire country, there were around 11.300 injured, and
approximately 35.000 crashed houses. Most of the material damages were
concentrated in Bucharest, were over 33 constructions and large buildings were
collapsed. The entire Zimnicea town was destroyed, and needed rebuilding from
the ground. Among the victims of the earthquake there were some notorious
persons such as the actor Toma Caragiu.
- August 30th, 1986 (12:28 AM), 7.1 degrees Richter, 131.4 km in depth
produced many damages in Basarabia, 4 apartment buildings collapsed in Chisinau.
- May 30th, 1990 (1:40 PM) 6.9 degrees Richter, 80-90 km in depth didnt cause
major damages;
- October 27th, 2004 (10:34 PM) 6.0 degrees Richter, 90-100 km in depth also,
didnt cause major damages.
In the area of Vrancea (analyses of the area in Ivan, 2007; Ivan, 2011; Ardelean,
1999) there are registered almost daily earthquakes under 3 degrees.

Characterizing the Frequency of Earthquake Incidence in Romania

__________________________________________________________________

3. STATISTIC PROCESSING OF DATA ON MAJOR SEISMIC EVENT

The registered data were processed firs of all, statistically descriptive. The results
as distribution series are presented in Table 1, the grouping being done in intervals
of 50 years.
Table 1 - The distribution of major seismic events in 50 years intervals
Number of
No.
Interval(years)
major seismic
events
1
1100 - 1150
2
2
1150 - 1200
2
3
1200 - 1250
1
4
1250 - 1300
1
5
1300 1350
1
6
1350 1400
0
7
1400 1450
1
8
1450 1500
1
9
1500 1550
2
10
1550 1600
5
11
1600 1650
5
12
1650 1700
2
13
1700 1750
5
14
1750 1800
4
15
1800 1850
7
16
1850 1900
8
17
1900 1950
7
18
1950 2000
4
19
2000 1
TOTAL
n = 59
The series (Table 1 and Figure 1) seems to suggest an acceleration of events in the
last 250 years: in the first decade D1 one earthquake was registered; Q 2 (M e ) = 2
earthquakes, and in D q 7 . This could be the effect of an energetic acceleration in
the intensity of the activity of the terrestrial crust, but most probably it is the result
of information inconsistencies in the medieval period which seem to suggest this
seismic intensification. The maximum value in an interval of 50 years is 8 major
seismic events (1850 1900). The total number of major earthquakes is 59. The
average in a 50 year interval is 3.11, with a standard deviation of = 2,45 and a
variation coefficient of CV = 0,788 which suggests a strong heterogeneity of the
observation series. Standard error = 0.561.
The shape of the series is completed with the values of the Skewness coefficient:

1 =

(s )
2

3/2

(where 3 is the centered moment of rank 3, and s2 the centered

Irina Maria Dragan, Alexandru Isaic-Maniu

__________________________________________________________________

4
moment of rank 2), and respectively 2 - Kurtosis coefficient: 2 =
(where
2

(s )
2

4 is the centered moment of rank 4).

1 = 0.7031
2 = 0.7794

Although it is considered that seismic events are rare events from a statistical
point of view, thus with reduced probabilities of occurrence, this hypothesis is not
confirmed for Romania (Figure 1).
Figure 1 - The Distribution of Earthquakes,
betw een 1100-2010 in Rom ania

7
5

5
4

4
1

years

The minimum value in a 50 year interval was 0 (1350-1400), and the maximum
number of earthquakes 8 - was registered between 1850 and 1900. The value of
the second quartile was 2, and Q1 = 1 and Q3 =5 respectively.

4. STATISTIC MODELING OF THE SEISMIC OCCURRENCE PROCESS

In order to analyze the process of earthquake occurrence, we tested several
distribution laws, obviously starting with the law of rare events Poisson,
continuing with the exponential law (Evans, 2000) and Weibul (Isaic-Maniu,
1983). The best results were obtained for the log-logistic statistic model (Johnson,
Kotz and Balakrishnan, 1995; Evans and Hastings, 2000; Stephens, 1979; Paiva,
1984; Ahmad, Sinclair and Werritty, 1988) by filtering three different selection
tests. The statistic literature contains various forms of this model with different
degrees of complexity. Thus, a variant has:
Parameters Distribution
- Continuous shape parameter ( > 0)

- Continuous scale parameter ( > 0)

Characterizing the Frequency of Earthquake Incidence in Romania

__________________________________________________________________

- Continuous location parameter ( 0 yields the two-parameter Log-Logistic

distribution)
Domain

x+

Three-Parameter Log-Logistic Distribution

Probability Density Function (PDF)

x
f (x ) =

x
1 +

(1)

Cumulative Distribution Function (CDF):

F ( x ) = 1 +
x

(2)

In the case that = 0 the probability density of this bi-parametric model is:

/ )( x / ) 1
(
f (x : , ) =
[1 + (x / ) ]2

(3)

where x > 0, > 0, > 0 and CDF:

( x / ) = x
F ( x : , ) =
=

+ x
1+ ( x / )
1+ ( x / )
1

(4)

The kth raw moment exists only when k < , when it is given by

k /
sin (k / )

( )

E X k = k B(1 k / , 1 + k / ) = k

(5)

where B() is the beta function. Expression for the mean, variance, Skewness and
Kurtosis can be derived from this. Writing b = / for convenience, the mean is

E ( X ) = b / sin b, > 1,

and the variance is

(6)

Var ( X ) = 2 2b / sin 2b b 2 / sin 2 b , > 2.

(7)
Explicit expressions for the Skewness and Kurtosis are lengthy. As tends to
infinity the mean tends to , the variance and Skewness tend to zero and the excess
Kurtosis tends to 6/5 (see also related distributions below).
The quantile function is:
1/

p
F ( p; , ) =

1 p
1

(8)

The log-logistic has been used as a simple model of the distribution of wealth or
income in economics, where Gini coeffcient is 1 / (Kleiber and Kotz, 2003) it is
known as the Fisk distribution. The log-logistic distribution provides one
parametric model for survival analysis. The survival function is

Irina Maria Dragan, Alexandru Isaic-Maniu

__________________________________________________________________

S ( t ) = 1 F ( t ) = 1 + ( x / )

(9)

and so the hazard function is

( / )( x / )
h (t ) =
=

S (t )
1+ ( x / )
f (t )

(10)

Generalized log-logistic or the three parameter log-logistic distribution. It has

also been called the generalized logistic distribution (Hosking, 1997), but this
conflicts with other uses of the term. It can be obtained from the log-logistic
distribution by addition of a shift parameter : if X has a log-logistic distribution
then X + has a shifted log-logistic distribution. So Y has a shifted log-logistic
distribution if log(Y ) has a logistic distribution. The shift parameter adds a
location parameter to the scale and shape parameters of the (unshifted) log-logistic.
In this parameterization, the cumulative distribution function (cdf) of the shifted
log-logistic distribution is

F ( x; , , ) =

(11)

(x )
1 + 1 +

for 1 + ( x ) / 0, where R is the location parameter, > 0 the scale

parameter and R the shape parameter. Note that some references use k =
to parameterize the shape.
The probability density function (pdf) is

1 /

(1 / +1)

(x )
1 +

(12)
F ( x; , , ) =
2
( x ) 1 /
1 + 1 +

again, for 1 + ( x ) / 0.
The shape parameter is often restricted to lie in [-1,1], when the probability
density functions is bounded. When > 1, it has an asymptote at x = / .
Reversing the sign of reflects the pdf and the cdf about x = 0.
See also:
when = / , the shifted log-logistic reduces to the log-logistic distribution.
when 0, the shifted log-logistic reduces to the logistic distribution.
The shifted log-logistic with shape parameter = 1 is the same as the generalized
Pareto distribution with shift parameter = 1 .

Characterizing the Frequency of Earthquake Incidence in Romania

__________________________________________________________________

5. VALIDATING THE DISTRIBUTION

In order to test the statistic nature of the distribution, we used the KolmogorovSmirnov, Anderson-Darling and Pearson-Fisher tests (Stephans, 1979;
www.mathwave.com; www.vosesoftware.com).
Kolmogorov-Smirnov
The test is defined for the hypothesis
H0: the distribution of earthquakes is log-logistic
H1: the distribution of earthquakes is not log-logistic.
We compute the empirical distribution function F ( x ) :

1 n
F ( x ) = I X i x
n i =1

(13)

where I X i x is the indicator function, equal to 1 if X i x and equal to 0 otherwise.

The Kolmogorov-Smirnov statistic for a given cumulative distribution function
F (x ) is

Dn = sup F ( x ) F ( x )

(14)

and F(x) the theoretical values of distribution.

The Dn computed value is compared to the maximum admitted equivalent.
The statistic computed value for the presented case resulted in Dn = 0,1941 is
inferior to the critical level 0.3612 for a significance level of = 0,01 .
The Anderson-Darling test is also a distance test, proposed by Wilbur Anderson
and Donald A. Darling in 1952.
The statistic of the test is
A2 = N S
(15)
where:
n

S =
i =1

( 2i 1) ln F
N

( X i ) + ln (1 F ( X n+1i ) )

(16)

in which F is the cumulative distribution function. For a significance level , we

validate one of the two hypotheses H0 and H1. The critical values for various
specified distributions are computed by Stephens (1979).
The value of the statistics of the test: 2.5023 confirms the log-logistic distribution
for = 0,01 .
Pearson-Fisher Statistic
Chi Square or Pearson-Fisher 2 test was proposed as a measure of random
departure between observation and the theoretical model by Karl Pearson (Pearson,
1900). The test was later corrected by Ronald Fisher trough decrease of the degrees
of freedom by a unit (decrease duet of the existence of the equality relationship
between the sum of observed frequencies and the sum of theoretical frequencies,
(Fisher, 1922)), and by the number of 692 unknown parameters of the theoretical

( )

Irina Maria Dragan, Alexandru Isaic-Maniu

__________________________________________________________________
distribution when they come as estimated from measures of central tendency
(Fisher, 1924).
The chi-square test is used to test if a sample of data came from a population with a
specific distribution. An attractive feature of the chi-square goodness-of-fit test is
that it can be applied to any uni-variate distribution for which you can calculate the
cumulative distribution function. The chi-square goodness-of-fit test is applied to
binned data (i.e., data put into classes).
The test is defined for the hypothesis
H0: The data follow a specific distribution
H1: The data do not follow the specific distribution
The statistic is calculated as (in original):
k
( x m )2 2
(Oi Ei )2
=
:

Ei
i =1
m

2 = S

(17)

where Oi is the observed frequency for bin i and Ei is the expected frequency for
bin i and is calculated by
Ei = N (F (Yu ) F (Yi ))
(18)
where F is the cumulative distribution function and Yu and Yi are the upper and
lower limits for class i.
The test statistic follows, approximately, a chi-square distribution with (k - c)
degrees of freedom where k is number of non-empty cells and c - the number of
estimated parameters for the distribution +1.
Therefore, the hypothesis that data are from a population with the specified
distribution is rejected if

2 > 2 ,k c
where , k c is the chi-square percent point function with k - c degrees of freedom
2

and a significance level of .

The computations lead to a value of the c2 statistic inferior to the critical value
02,01 = 6.635, so that the H0 hypothesis is accepted with a probability of 99%.

The three applied tests (Kolmogorov-Smirnov, Anderson-Darling and PearsonFisher) confirm with a high confidence degree the log-logistic distribution, by
parameters:
= 1.6112
= 1.9994
=0

The Probability Density Function (pdf) for the estimated values of the parameters
is presented in Figure 2, the Cumulative Distribution Function (cdf) in Figure 3,
and hazard function in Figure 4.
Table 2 presents the values of the main indicators of the log-logistic distribution for
a number of x = 0, , 10 events.

Characterizing the Frequency of Earthquake Incidence in Romania

__________________________________________________________________
Table 2 The Values for pdf, CDF, h(x) i S(x)
Values computed for x (earthquakes) equal to:

Statistic
Functions
pdfprobability
density
function
CDF cumulative
distribution
function
h(x) hazard
function
S(x) distribution

10

0.3033

0.2077

0.1238

0.0757

0.0488

0.0333

0.0234

0.0171

0.0129

0.01000

0.2467

0.3193

0.5001

0.6579

0.7535

0.8545

0.8828

0.9033

0.9186

0.9304

0.3975

0.4116

0.4029

0.3533

0.3035

0.2295

0.2032

0.1819

0.1645

0.1499

0.7533

0.4998

0.3421

0.2465

0.1859

0.1455

0.1172

0.0967

0.8814

0.0696

Figure 2
Probability Density Function
0,32
0,28
0,24

f(x)

0,2
0,16
0,12
0,08
0,04
0
0

0,8

1,6

2,4

3,2

4,8

x
Log-Logistic (1,6112; 1,9994)

5,6

6,4

7,2

Irina Maria Dragan, Alexandru Isaic-Maniu

__________________________________________________________________
Figure 3
Cumulative Distribution Function
0,88
0,8
0,72
0,64

F(x)

0,56
0,48
0,4
0,32
0,24
0,16
0,08
0
0

0,8

1,6

2,4

3,2

4,8

5,6

6,4

7,2

5,6

6,4

7,2

x
Log-Logistic (1,6112; 1,9994)

Figure 4
Hazard Function
0,4
0,36
0,32

h(x)

0,28
0,24
0,2
0,16
0,12
0,08
0,04
0
0

0,8

1,6

2,4

3,2

4,8

x
Log-Logistic (1,6112; 1,9994)

Characterizing the Frequency of Earthquake Incidence in Romania

__________________________________________________________________
6. CONCLUSIONS
In the followings, through simulation operations for the values of the log-logistic
distribution, we formulate various hypotheses on the occurrence of seismic events,
for the confirmed statistic model.
Thus, if we limit, for a 50 year interval, the number of major seismic events to
x1 = 1 and x2 = 3 respectively, we have:
P (x < x1) = 24,67 %
P (x > x1) = 75,33 %
P (x1 < x < x2) = 41,112 %
P (x < x2) = 62,79 %
P (x > x2) = 34,22 %
It is an optimistic variant that the chances for less than one major seismic event to
occur in a 50 year interval are around 25%, and for more than 3 major seismic
events, over 34%.
If we modify the limits to x1 = 8 and x2 = 10 major seismic events, then:
P (x < x1) = 90,33 %
P (x > x1) = 9,67 %
P (x1 < x < x2) = 2,72 %
P (x < x2) = 93 %
P (x > x2) = 6,96 %
So, there is a high probability that in Romania, less than 8 earthquakes will occur,
and very slim chances that more than 10 earthquakes will occur. There is a
probability of approximately 3% that in an interval of 50 years, between 8 and 10
events could occur.
Romania represents an unique case in the world, from a seismic point of view:
earthquakes of over 7 degrees Richter in magnitude which originate from Vrancea
affect approximately 50% of the territory and approximately 60% of the
population, including Bucharest. Nonetheless, the earthquake in 1977 was not the
most powerful. It was only the fourth in magnitude among the earthquakes in the
last 200 years. In Romania, there were 6 earthquakes of over 7 degrees Richter in
the last 200 years. More technical details on the area Vrancea can be found in Ivan
(2007, 2011).
In the case of Romania, the warning period for an earthquake is 25-30 second,
which is relatively short in comparison to Mexico City - 60 seconds. However, it is
enough to interrupt dangerous activities: nuclear reactors, heavy water production,
chemical industry, gases, electricity and water. For trains and subways, stopping
the electrical power is enough to stop the carriages.
REFERENCES
[1] Abo-Eleneen, Z., Nigm, E., M. (2010), Estimation of the Parameters of the
Reversed Generalized Logistic Distribution with Progressive Censoring Data.
International Journal of Mathematics and Mathematical Sciences, Hindwai
Publishing Corporation;

Irina Maria Dragan, Alexandru Isaic-Maniu

__________________________________________________________________
[2] Ahmad, M., I., Sinclair, C., D., Werritty, A. (1899), Log-logistic Flood
Frequency Analysis. Journal of Hydrology 98: 205-224, doi:10.1016/00221694(88)9001;
[3] Anderson, T., W., Donald, A., Darling (1952), Asymptomatic Theory of
Certain Goodness-of-fit Criteria Based on Stochastic Processes. Journal of the
American Statistical Association, 69, 730-737;
[4] Ardeleanu, L. (1999), Modelarea fenomenelor de und generate de
cutremurele din regiunea Vrancea . PhD thesis, University of Bucharest;
[5] Ashkar, F., Mahdi, S. (2006), Fitting the Log-logistic Distribution by
Generalized Moments; Journal of Hydrology 328: 694-703;
[6] Collett, D. (2003), Modelling Survival Data in Medical Research, CRC press;
[7] Constantinescu, L., Mrza, V., I. (1980), A Computer-compiled and
Computer-oriented Catalogue of Romanias Earthquakes during a Millennium.
(A D 984-1979), Rev. Roum. Geophysique Teme 24, No. 2, Bucharest, 193-206;
[8] Corder, G., W., Foreman, D., I. (2009), Nonparametric Statistics for Non
Statisticians: A step-by-step Approach. Wiley, New York;
[9] Dragomir, C. (2009), O scioantropologie a dezastrelor naturale;Lumen
Publishing, Iai;
[10]Evans, M., Hastings, N., Peacock, B. (2000), Statistical Distributions. (3rd
ed.), New York: John Wiley;
[11]Evans, M., Hastings, N., Peacock, B. (1993), Statistical Distributions, 2nd
ed., Hoboken, John Wiley & Sons, Inc.;
[12]Fisher, R., A. (1924), The Conditions under which 2 Measures the
Discrepancy Between Observation and Hypothesis: J. Roy Statist. Soc. 87, 442450;
[13]Fisher, R., A. (1922), On the Interpretation of 2 from Contingency Tables,
and the Calculation of P. Journal of the Royal Statistical Society 85:87-94;
[14]Geskus, R. (2001), Methods for Estimating the AISD Incubation Time
Distribution when Date of Seroconversion is Censored. Statistics in Medicine 20
(5): 795-812;
[15]Giurcneanu, C. (1986), nfruntnd natura dezlnuit, Albatros Publishing,
Bucharest;
[16]Hosking, J., Wallis, R. (1997), Regional Frequency Analysis: An Approach
Based on L-Moments. Cambrige University Press;
[17]Isaic-Maniu, Al. (2009), Gauss` Bell Rings Forever .Economic Computation
and Economic Cybernetics Studies and Research, Vol. 43, , page 237;
[18]Isaic-Maniu, Al. (2008), Some Comments on an Entropy - Like
Transformation of Soleha and Sewilam. Economic Computation and Economic
Cybernetics Studies and Research, no. 1-2, 5-11;
[19]Isaic-Maniu, Al. (1983), Metoda Weibull. Academiei Publishing, Bucharest;
[20]Ivan M. (2011), Crustal thickness in Vrancea Area, Romania from S to P
Convert Waves. Journal of Seismology, Springer, published online 14 January;
[21]Ivan, M. (2007), Attenuation of P and pP Waves in Vrancea Area
Romania .Journal of Seismology, Springer, Vol. 11(1), pp. 73-85;

Characterizing the Frequency of Earthquake Incidence in Romania

__________________________________________________________________
[22]Johnson, N., L., Balakhrisnan, N., Kotz, S. (2000), Continuous Multivariate
Distributions. Vol. 1, Hoboken, NJ: Wiley-Interscience;
[23]Johnson, N., L., Kotz, S., Balakrishnan, N. (1994), Continuous Univariate
Distributions. Vol. 2, John Wiley Publishing, New York;
[24]Kantam, R., R., L., Srinivasa Rao, G., Sriram, B. (2006), An Economic
Reliability Test Plan: Log-logistic Distribution; Journal of Applied Statistics,
1360-0532, Volume 33, Issue 3, page 291-296;
[25]Kleiber, C., Kotz, S. (2003), Statistical Size Distributions in Economics and
Actuarial Sciences . Wiley, New York ;
[26]Lungu, D., Aldea, A., Demetriu, S., Caraifaleanui, I. (2004), Seismic
Strengthening of Buildings and Seismic Instrumentation - two Priorities for
Seismic Risk Reduction in Romania. Acta Geodactica et Geophysica Hungarica,
Vol. 39, No. 2-3, May, 253-258;
[27]Lungu, D., Arion, C., Baur, M., Aldea, A. (2000), Vulnerability of Existing
Building Stock in Bucharest. 6ICSZ Sixth International Conference on Seismic
Zonation, Palm Springs, California, USA, Nov. 12-15, 873-846;
[28]Lungu, D. (1999), Seismic Hazard and Countermeasures in BucharestRomania. Bulletin of the International Institute of Seismology and Earthquake
Engineering IISEE, Tsukuba, Japan, Vol. 33, 341-373;
[29]Lungu, D., Arion, C., Aldea, A., Demetriu, S. (1999), Assessment of Seismic
Hazard in Romania Based on 25 Years of Strong Ground Motion
Instrumentation; NATO ARW Conference on strong motion instrumentation for
civil engineering structures, Istanbul, Turkey, June 2-5, 1999;
[30]Paiva Franco, M., A. (1984), A Log Logistic Model for Survival Time with
Covariantes. Biometrika, Vol. 71, issue 3, 621-623;
[31]Radulian, M. (2004), Impactul cutremurelor din regiunea Vrancea asupra
securitii oraului Bucharest i a altor zone urbane adiacente. Research
Contract CNCSIS, 2004, Bucharest;
[32]Scuiu, I., Zorilescu, D. (1978), Numere aleatoare. Aplicaii n economie,
industrie i studiul fenomenelor naturale. Academiei Publishing, Bucharest;
[33]Stephens, M., A. (1979), Test of Fit for the Logistic Distribution Based on
the Empirical Distribution Function. Biometrika, Vol. 66, 591-595;
[34]Venter, G. (1994), Introduction to Selected Papers from the Variability in
Reserves Prize Program, available at:
(http://www.casact.org/pubs/forum/94spforum/94spf091.pdf);
[35]Vod Cristina, Isaic-Maniu, Al. (1983), O aplicaie a modelului Weibull n
studiul fenomenelor seismice. Mathematics Gazette, year IV, No. 1-2, 68-73,
Bucharest;
[36]Weisstein, E. W. (2005), Anderson-Darling Statistic; MathWorld - A
Wolfram Web Resource, http://mathworld.wolfram.com;
[37]www.incerc2004.ro
[38]www.mdrl.ro
[39]www.nist.gov/itl/
[40]www.weibull.com
[41]www.wessa.net
[42]www.maplesoft.com.